ID  - esann16zeroshot
T1  - Using Semantic Similarity for Multi-Label Zero-Shot Classification of Text Documents
A1  - Sappadla, Prateek Veeranna
A1  - Nam, Jinseok
A1  - Loza Mencía, Eneldo
A1  - Fürnkranz, Johannes
TI  - Proceedings of the 23rd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN-16)
Y1  - 2016
PB  - d-side publications
AD  - Bruges, Belgium
UR  - https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2016-174.pdf
N2  - In this paper, we examine a simple approach to zero-shot multi-label
text classification, i.e., to the problem of predicting multiple, possibly previously
unseen labels for a document. In particular, we propose to use a semantic embed-
ding of label and document words and base the prediction of previously unseen
labels on the similarity between the label name and the document words in this em-
bedding. Experiments on three textual datasets across various domains show that
even such a simple technique yields considerable performance improvements over
a simple uninformed baseline.
ER  -